[Swizec]

> As far as I could tell, nothing was substantially different from the Ellsworth translation and the Fable translation.

Crucially the full translation was part of ChatGPT’s training set. Recall is a pretty solved problem in machine learning.

How well does it translate a French novel published yesterday? Where neither the original novel nor any translations are in the training set yet? Or might not even exist!

I tried asking ChatGPT to translate a letter I wrote in Slovenian this weekend. It got the general gist but missed a lot of the nuance. Completely missed several of the little touches of tone where the right choice of synonym conveys a whole bunch of information.

[tombert]

Did no one actually finish reading my comment?

[Swizec]

I feel like that wasn’t there when I started writing my comment. I also have a bad habit of quickly posting and then adding over a few minutes.

Glad we agree :)

[tombert]

Guess I have no way of proving it, but I pinky swear that I didn't edit it in later!

But yeah, I broadly do agree; if I read other languages I could find a book that hadn't been thoroughly translated to English and then I could give a proper analysis on how good the translation is, but since I'm a very stereotypical American I know exactly one language (and sometimes my comprehension of even that is questionable).

[Hendrikto]

> I could find a book that hadn't been thoroughly translated to English and then I could give a proper analysis on how good the translation is, but since I'm a very stereotypical American I know exactly one language

So you actually cannot give a proper analysis.

[zipy124]

Welcome to the internet